© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 127246
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or expressions involving parentheses and braces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing parenthesis followed by an identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diss
    -0.37
     Cela
    -0.37
     fati
    -0.37
     wond
    -0.37
    hecta
    -0.36
     dispers
    -0.36
     grate
    -0.36
     deter
    -0.36
     Kite
    -0.35
     bitumen
    -0.35
    POSITIVE LOGITS
    )_{
    1.77
    })_{
    1.72
    ]_{
    1.27
    )_{\
    1.24
    )_
    1.10
    \}_{
    1.05
    ]_{\
    1.03
    \|_{
    0.89
    ]_
    0.86
    |_{
    0.83
    Activations Density 0.075%

    No Known Activations